129 lines
3.0 KiB
JSON
129 lines
3.0 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.0,
|
|
"eval_steps": 100,
|
|
"global_step": 108,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.009259259259259259,
|
|
"grad_norm": 17.74639892578125,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.4363,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.09259259259259259,
|
|
"grad_norm": 5.17479944229126,
|
|
"learning_rate": 1.6363636363636366e-05,
|
|
"loss": 3.0187,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.18518518518518517,
|
|
"grad_norm": 9.653449058532715,
|
|
"learning_rate": 1.9666208503126115e-05,
|
|
"loss": 2.3473,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.2777777777777778,
|
|
"grad_norm": 8.364947319030762,
|
|
"learning_rate": 1.8348280530292712e-05,
|
|
"loss": 2.076,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.37037037037037035,
|
|
"grad_norm": 4.204029560089111,
|
|
"learning_rate": 1.6162284656009276e-05,
|
|
"loss": 1.8518,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.46296296296296297,
|
|
"grad_norm": 2.5657479763031006,
|
|
"learning_rate": 1.3335524316508208e-05,
|
|
"loss": 1.743,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.5555555555555556,
|
|
"grad_norm": 2.2198078632354736,
|
|
"learning_rate": 1.0161930688025018e-05,
|
|
"loss": 1.6929,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.6481481481481481,
|
|
"grad_norm": 1.653656005859375,
|
|
"learning_rate": 6.971499241020495e-06,
|
|
"loss": 1.6575,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.7407407407407407,
|
|
"grad_norm": 1.443210244178772,
|
|
"learning_rate": 4.095976269940777e-06,
|
|
"loss": 1.6358,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 1.2429494857788086,
|
|
"learning_rate": 1.8343633694278895e-06,
|
|
"loss": 1.6261,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.9259259259259259,
|
|
"grad_norm": 1.2830959558486938,
|
|
"learning_rate": 4.218267581201296e-07,
|
|
"loss": 1.6122,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.9259259259259259,
|
|
"eval_loss": 1.625947117805481,
|
|
"eval_runtime": 2.4059,
|
|
"eval_samples_per_second": 324.208,
|
|
"eval_steps_per_second": 2.91,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"step": 108,
|
|
"total_flos": 4.017624413372416e+16,
|
|
"train_loss": 1.907559284457454,
|
|
"train_runtime": 456.0106,
|
|
"train_samples_per_second": 30.304,
|
|
"train_steps_per_second": 0.237
|
|
}
|
|
],
|
|
"logging_steps": 10,
|
|
"max_steps": 108,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 200,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 4.017624413372416e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|